Title
A Simplified Intelligent Autonomous Obstacle Bypassing Method for Mobile Robots
System Model
Abstract
This paper presents a demo focusing on developing a robot capable of autonomously bypassing obstacles in cluttered environments using a camera as its sole sensing mechanism. The robot is programmed to follow a predetermined path via a line following module while using a custom object detection model to detect and differentiate obstacles on the road from other objects in the environment. The obstacle detection module based on YOLOv5 architecture can accurately detect obstacles from the surrounding. Upon obstacle detection, the robot initiates an obstacle avoidance maneuver by adjusting its steering based on error measurement, allowing it to navigate around the obstacle smoothly. The proposed design is validated with extensive experimentation, demonstrating its ability to navigate cluttered environments while avoiding obstacles.
Index Terms
Mobile Robots, Image Processing, Autonomous Navigation.
Acknowledgements
This work was supported by the projects EU-ICT IntellIoT (grant agreement No. 957218) and Infotech-R2D2.
Afiliation
Centre for Wireless Communication, University of Oulu, Finland